From consumer perception characterization to human centered industrial product design

In this paper, we present a general approach for helping designers to develop new human centered industrial products using intelligent techniques. First, we characterize and evaluate consumer perception on industrial products, which is composed of two levels: basic perception independent of the socio-cultural context of these products, and complex socio-cultural concepts integrated into these products. The related human evaluation data are modeled and analyzed using fuzzy sets. Next, the complex relations between these two levels of perception as well as the physical design parameters of industrial products are modeled using decision trees and a fuzzy cognitive map. The decision trees are used for setting up an empirical model from learning data measured and evaluated on a set of representative samples while the fuzzy cognitive map permits to build a conceptual model from professional knowledge of experts. These models are then combined so that these two different information sources can be used in a complementary way in order to form a more complete model. Based on these models, we can analyze relations of products and consumers in order to obtain a suitable market segmentation and find relevant product parameters according to specific requirements of consumers at different levels.